Evaluating the Semantic Specificity of Representation Steering in Language Models

• URL: http://arxiv.org/abs/2608.29431v1
• Date: Sat, 29 Aug 2026 20:31:32 GMT
• Title: Evaluating the Semantic Specificity of Representation Steering in Language Models
• Abstract summary: Localized Representation Steering is widely used to correct reasoning pathologies in large language models.<n>Standard benchmark evaluations can easily be fooled by superficial label overrides, creating a false impression of reasoning circuit repairs.
• Score: 11.464730765998555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Localized Representation Steering (LRS) is widely used to correct reasoning pathologies in large language models. However, standard benchmark evaluations can easily be fooled by superficial label overrides, creating a false impression of reasoning circuit repairs. In this work, we propose Cross-Rule Transfer (CRT), a diagnostic framework that audits representational interventions by evaluating them on rule families where the model is natively competent. Evaluating late-layer LRS for a widespread logical failure, contradiction blindness, reveals that the intervention merely injects a global label bias: applying the steering vector to rules the model already handles correctly (99.6% baseline) degrades performance to 40.4% by forcing false contradiction predictions. We support this diagnosis with four complementary controls (direct logit bias equivalence, control vector label-flipping, cross-model grafting, and early-layer steering checks), providing a rigorous methodology to distinguish genuine reasoning repairs from superficial label overrides.

Related papers

• MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs [16.970480774847857]
  We define Proactive Critique as the model's autonomous ability to identify, analyze and fix faulty user inputs without extra prompts.<n>We propose MMPCBench, a comprehensive framework for evaluating MLLMs' proactive critique competence.<n>It features a fine-grained taxonomy of 4 primary error types spanning 12 subcategories, ranging from cross-modal contradictions to missing visual premises.
  arXiv  Detail & Related papers  (2026-08-29T14:19:10Z)
• Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation [14.043179860831406]
  Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal.<n>We propose Trajectory-Augmented Policy Optimization (TAPO), which advances self-distillation from implicit distributional alignment to explicit trajectory construction.
  arXiv  Detail & Related papers  (2026-06-17T09:24:19Z)
• Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models [55.788110316999166]
  We compare reasoning models produced via supervised fine-tuning, RL-based post-training, and distillation against instruction-tuned baselines.<n>We observe that reasoning models often improve on reasoning benchmarks but exhibit alignment regressions.<n>These regressions are consistent with behavioral drift from the instruction-tuned baseline, measured by KL divergence.
  arXiv  Detail & Related papers  (2026-06-09T16:14:27Z)
• SAAG: Structured Agent Assessment and Grounding [13.62148061055744]
  We propose a cascaded diagnostic framework that decomposes agent-calling evaluation into three sequential stages.<n>We evaluate this framework on a benchmark derived from Glaive's function-calling dataset across registry sizes of 5, 10, and 15 agents.
  arXiv  Detail & Related papers  (2026-04-30T19:33:58Z)
• Decoding the Critique Mechanism in Large Reasoning Models [50.821607345799386]
  Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions.<n>We investigate how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps.<n>We find that despite the error propagating through the chain-of-thought, the model still reaches the correct final answer.
  arXiv  Detail & Related papers  (2026-03-17T10:03:30Z)
• LLM Reasoning Predicts When Models Are Right: Evidence from Coding Classroom Discourse [0.18268488712787334]
  Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale.<n>We investigate whether reasoning generated by LLMs can be used to predict the correctness of a model's own predictions.<n>We analyze 30,300 teacher utterances from classroom dialogue, each labeled by multiple state-of-the-art LLMs with an instructional move construct and an accompanying reasoning.
  arXiv  Detail & Related papers  (2026-02-10T14:38:13Z)
• Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification [49.506412445511934]
  Large Language Models (LLMs) show remarkable capabilities, yet their next-token prediction creates logical inconsistencies and reward hacking.<n>We introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process.<n>We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization.
  arXiv  Detail & Related papers  (2026-01-30T07:01:25Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• Cognitive bias in LLM reasoning compromises interpretation of clinical oncology notes [28.87443673774825]
  We developed a hierarchical taxonomy of reasoning errors from GPT-4 chain-of-thought responses to real oncology notes.<n>We validated the taxonomy on 822 responses from prostate cancer consult notes spanning localized through metastatic disease.<n> Reasoning failures were associated with guideline-discordant and potentially harmful recommendations.
  arXiv  Detail & Related papers  (2025-11-16T21:13:09Z)
• ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization [73.0780809974414]
  We propose a Reflective Autoformalization method that integrates semantic consistency evaluation into the autoformalization process.<n>This enables the model to iteratively generate formal statements, assess its semantic fidelity, and self-correct identified errors.<n>Experiments show that ReForm achieves an average improvement of 22.6 percentage points over the strongest baselines.
  arXiv  Detail & Related papers  (2025-10-28T16:22:54Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.931194824519935]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.